Microbiome and pancreatic cancer: time to think about chemotherapy.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer characterized by late diagnosis, rapid progression, and a high mortality rate. Its complex biology, characterized by a dense, stromal tumor environment with an immunosuppressive milieu, contributes to resistance against standard treatments like chemotherapy and radiation. This comprehensive review explores the dynamic role of the microbiome in modulating chemotherapy efficacy and outcomes in PDAC. It delves into the microbiome's impact on drug metabolism and resistance, and the interaction between microbial elements, drugs, and human biology. We also highlight the significance of specific bacterial species and microbial enzymes in influencing drug action and the immune response in the tumor microenvironment. Cutting-edge methodologies, including artificial intelligence, low-biomass microbiome analysis and patient-derived organoid models, are discussed, offering insights into the nuanced interactions between microbes and cancer cells. The potential of microbiome-based interventions as adjuncts to conventional PDAC treatments are discussed, paving the way for personalized therapy approaches. This review synthesizes recent research to provide an in-depth understanding of how the microbiome affects chemotherapy efficacy. It focuses on elucidating key mechanisms and identifying existing knowledge gaps. Addressing these gaps is crucial for enhancing personalized medicine and refining cancer treatment strategies, ultimately improving patient outcomes.

Deep Neural Networks and Tabular Data: A Survey.

Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous datasets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains highly challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized architectures, and regularization models. For each of these groups, our work offers a comprehensive overview of the main approaches. Moreover, we discuss deep learning approaches for generating tabular data and also provide an overview over strategies for explaining deep models on tabular data. Thus, our first contribution is to address the main research streams and existing methodologies in the mentioned areas while highlighting relevant challenges and open research questions. Our second contribution is to provide an empirical comparison of traditional machine learning methods with 11 deep learning approaches across five popular real-world tabular datasets of different sizes and with different learning objectives. Our results, which we have made publicly available as competitive benchmarks, indicate that algorithms based on gradient-boosted tree ensembles still mostly outperform deep learning models on supervised learning tasks, suggesting that the research progress on competitive deep learning models for tabular data is stagnating. To the best of our knowledge, this is the first in-depth overview of deep learning approaches for tabular data; as such, this work can serve as a valuable starting point to guide researchers and practitioners interested in deep learning with tabular data.

Apoptosis-mediated endothelial toxicity but not direct calcification or functional changes in anti-calcification proteins defines pathogenic effects of calcium phosphate bions.

Calcium phosphate bions (CPB) are biomimetic mineralo-organic nanoparticles which represent a physiological mechanism regulating the function, transport and disposal of calcium and phosphorus in the human body. We hypothesised that CPB may be pathogenic entities and even a cause of cardiovascular calcification. Here we revealed that CPB isolated from calcified atherosclerotic plaques and artificially synthesised CPB are morphologically and chemically indistinguishable entities. Their formation is accelerated along with the increase in calcium salts-phosphates/serum concentration ratio. Experiments in vitro and in vivo showed that pathogenic effects of CPB are defined by apoptosis-mediated endothelial toxicity but not by direct tissue calcification or functional changes in anti-calcification proteins. Since the factors underlying the formation of CPB and their pathogenic mechanism closely resemble those responsible for atherosclerosis development, further research in this direction may help us to uncover triggers of this disease.